Results
41 articlesSort
38:47EN
Theo - t3․gg· Oct 28, 2026Theo’s Long-Running Agent Experiments: Verification, Compute and CostTheo Browne · Ping LabsA skateboard game and two compiler projects show how repeated checks and flexible compute can sustain agent work—and how expensive those loops can become.
36:07ENTheo - t3․gg· Oct 27, 2026Theo on Token Costs, Coding Agents, and the Price of AI CapabilityTheo Browne · Ping LabsA viral estimate of Lauren's AI spending prompts a closer look at cache pricing, benchmarks, and the changing work of coding agents.
38:30ENTheo - t3․gg· Oct 14, 2026Theo Tests Gemini 4 Argon: Design Strengths and Code-Review ConcernsTheo Browne · Ping LabsA strong result on a narrow skateboarding benchmark contrasts with poor findings in Theo’s own codebase audits.
38:02ENTheo - t3․gg· Oct 13, 2026Meta’s Muse Wonder Full: A Coding Agent Tested Against Opus and SolTheo Browne · Ping LabsTheo Browne tests Meta’s new model on code review, debugging, delegation and benchmarks, finding promising strengths alongside important limits.
18:18ENTheo - t3․gg· Oct 12, 2026Why AI Bills Can Rise as Intelligence Gets CheaperTheo Browne · Ping LabsTheo Browne explains the difference between token prices, task costs and capability, and why more useful agents can still drive larger bills.
0:23ENTheo - t3․gg· Oct 12, 2026Why Theo Would Wait Before Upgrading for UltrafastTheo Browne · Ping LabsA short cost comparison leads Theo Browne to caution against upgrading to the $500 tier solely for Astra Ultrafast.
41:10ENTheo - t3․gg· Oct 9, 2026Haiku 5.5: Where a Cheaper Small Model Helps Coding AgentsTheo Browne · Ping LabsTheo Browne examines Haiku 5.5 pricing, benchmark results and practical tests, including a failed pull-request audit.
33:33ENTheo - t3․gg· Oct 7, 2026Is the $200 Codex Plan Still Worth It?Theo Browne · Ping LabsTheo Browne compares subscription usage, API-equivalent estimates, model efficiency and the cost of Ultrafast.
0:29ENTheo - t3․gg· Oct 7, 2026Theo’s Ultrafast Test: $600 of Usage for Two PR ReviewsTheo Browne · Ping LabsA short example illustrates how quickly token costs can rise when using Ultrafast for everyday review work.
28:17ENTheo - t3․gg· Oct 6, 2026Ultrafast Coding: A Live Design Loop With a Steep CostTheo Browne · Ping LabsTheo Browne explores how fast inference changes his workflow, and why he still advises against upgrading solely for Ultrafast.
1:06:36ENTheo - t3․gg· Oct 2, 2026Theo’s Guide to Running Coding Agents in ParallelTheo Browne · T3Theo explains his approach to subscription usage, agent delegation, review and remote machines, while acknowledging that parts of his setup may violate provider rules.
30:58ENTheo - t3․gg· Sep 29, 2026GPT-6.1 Sol: Cheap, Thorough at Code Review, but Uneven at Long BuildsTheo Browne · T3Theo compares early tests of GPT-6.1 Sol with competing models, from benchmark cost to real code reviews and a 3D game demo.
31:46ENTheo - t3․gg· Sep 29, 2026Claude Sonnet 5.5: A Fast Research Assistant for Coding AgentsTheo Browne · T3Theo tests Sonnet 5.5 on pricing, reasoning effort, codebase analysis and a 3D game, and finds a surprising role for it alongside larger models.
0:31ENTheo - t3․gg· Sep 24, 2026Grok 4.7’s Token Use and the Claims Around Its ReleaseTheo Browne · T3Theo compares Elon Musk’s earlier predictions for Grok 4.7 with selected benchmark results and token counts.
40:14ENTheo - t3․gg· Sep 23, 2026Opus 5.5: Theo’s First Day with a New Coding ModelTheo Browne · T3Theo compares price, benchmarks, coding work and game demos while cautioning that his assessment rests on a single day of use.
27:53ENTheo - t3․gg· Sep 22, 2026Grok 4.7: Strong Codebase Investigation, Uneven ValueTheo Browne · T3Theo compares launch claims, token costs, benchmarks and his own codebase and game tests, finding useful review behavior alongside significant tradeoffs.
30:29ENTheo - t3․gg· Sep 21, 2026Jev: A Fast Classifier for Structured DecisionsTheo Browne · T3Theo Browne explores Typesafe AI’s Jev through classification, game and developer-workflow demos, and explains where he thinks a reasoning model is still needed.
27:09ENTheo - t3․gg· Sep 18, 2026Why Theo Values Reliable Coding Agents Over Peak PerformanceTheo Browne · T3Theo Browne argues that a model’s weakest moments matter when a coding task stretches from investigation through testing and review.
0:36ENTheo - t3․gg· Aug 28, 2026Theo on Ox Alpha, Revealed as GLM-5.3-FlashTheo Browne · Ping LabsTheo discusses the model’s price, multimodal inputs and Chinese-chip deployment in a short first impression.
25:31ENTheo - t3․gg· Aug 13, 2026Grok 4.6: Better Agent Benchmarks, With Tradeoffs in Speed and CostTheo Browne · t3.ggTheo Browne tests Grok 4.6 on design, games and real code, weighing reported benchmark gains against his experience of slower and costlier tasks.
44:42ENTheo - t3․gg· Aug 7, 2026Theo Tests Meta’s Muse Code: Fast, Cheap and UnevenTheo Browne · Ping LabsMuse Spark 1.2 handles rapid analysis and pull-request triage at low cost, but Theo’s experiments expose integration failures, hallucinations and rate limits.
36:00ENTheo - t3․gg· Jul 26, 2026Theo on Kimi K3, Distillation and the Open-Weight AI DebateTheo Browne · Ping LabsKimi K3’s capabilities have sparked arguments over model distillation, security and competition. Theo separates the practical tradeoffs from his own speculation about lab strategy.
44:29ENTheo - t3․gg· Jul 25, 2026Theo’s Opus 5 Review: Coding Style, Cost and Model TradeoffsTheo Browne · Ping LabsAfter a day of coding with Opus 5, Theo compares it with Fable and GPT-5.6 Sol across plans, benchmarks, costs and real work.
57:39ENTheo - t3․gg· Jul 18, 2026Fable 5 vs GPT-5.6 Sol: Theo on Cost, Coding and Model JudgmentTheo Browne · Ping LabsTheo compares two coding models through benchmarks, design work and long-running tasks, explaining why his favorite model is not always the one he uses first.Load moreShowing 24 of 41